TypeError: can't pickle _thread.lock objects in Seq2Seq

The problem is with latest changes in seq2seq.py. Add this to your script and it will avoid deep-coping of the cells:

setattr(tf.contrib.rnn.GRUCell, '__deepcopy__', lambda self, _: self)
setattr(tf.contrib.rnn.BasicLSTMCell, '__deepcopy__', lambda self, _: self)
setattr(tf.contrib.rnn.MultiRNNCell, '__deepcopy__', lambda self, _: self)